Senior Machine Learning Engineer

Location: Philadelphia, PA

Onsite Flexibility: Onsite

• Position Type: Right to Hire (Contract-to-Hire)
• Pay Rate: $70.00 $ 75.00 / Hour (USD)
• Work Authorization: Applicants must be authorized to work for ANY employer in the U.S. We are unable to sponsor or take over sponsorship of an employment Visa at this time.

We are looking for a Senior Machine Learning Engineer to work hands-on on machine learning, predictive modeling, scoring, decisioning, and applied AI initiatives. This role is focused on building, validating, deploying, and improving machine learning models as a strong individual contributor, working alongside senior technical leadership who will help shape problem definition and overall model strategy.

This is a hands-on model-building role. The ideal candidate should be comfortable spending most of their time working directly with data, features, models, scoring logic, validation methods, production workflows, and model improvement and should bring solid engineering judgment, ownership of their deliverables, and the ability to drive their work forward without waiting for perfect requirements.

We are especially interested in candidates with experience building predictive scores, risk scores, health scores, engagement scores, prioritization models, or similar decision-support systems. Experience with transparent, interpretable, and explainable models is valuable, especially in environments where business trust, auditability, and operational adoption matter.

This is a fast-moving, startup-like environment. Requirements may be incomplete and priorities may evolve; the right candidate is comfortable iterating quickly and helping create clarity within their own workstream. A background in commercial software, SaaS, digital products, fintech, healthtech, consumer technology, or other product-driven environments is preferred.

Experience with Generative AI is also useful, especially where LLMs, RAG, summarization, conversational AI, agents, document intelligence, or AI-enabled workflow automation can complement traditional predictive models and scoring systems.

The Top Three Things We Are Looking For:

1. Strong Hands-On Production ML Builder The right candidate must be able to personally build models. They should be comfortable taking messy data and a defined prediction problem and turning it into a working, validated, usable model including feature engineering, model training, validation, calibration, thresholding, monitoring, production scoring, and model improvement.

2. Product and Commercial Software Mindset The right candidate should think beyond model performance and understand how models become useful product capabilities: who will use the model, what decision it supports, what action it should trigger, and how success will be measured. Experience in commercial software, SaaS, fintech, healthtech, consumer products, fraud, credit, pricing, personalization, or similar product-driven environments is valuable.

3. Experience with Transparent Scoring and Decisioning Because this role supports scores and decisioning systems, we value candidates who have built models that people can understand, trust, monitor, and act on scorecards, risk scores, health scores, calibrated models, score bands, thresholds, and business-facing model explanations. Strong candidates without direct scorecard experience but with solid interpretable-modeling fundamentals will also be considered.

Hands-On Model Development

• Build, test, validate, and improve machine learning models for scoring, prediction, prioritization, risk detection, engagement, and decision support.
• Perform exploratory data analysis, data quality assessment, feature engineering, model training, model selection, and performance evaluation.
• Develop practical models that balance predictive performance, explainability, stability, maintainability, and business usefulness.
• Work with structured, semi-structured, and operational data to create model-ready datasets and reusable features.
• Use tools such as Python, SQL, Spark, Databricks, MLflow, scikit-learn, XGBoost, or similar platforms and libraries.
• Move quickly from data exploration to prototype to validated model to production-ready capability.

Scoring and Transparent Models

• Implement predictive scores, risk tiers, score bands, thresholds, cut points, and intervention logic based on agreed designs.
• Build transparent and interpretable models where explainability matters, including logistic regression, GLMs, decision trees, calibrated models, or explainable boosting approaches.
• Evaluate models for accuracy, calibration, stability, drift, and operational usefulness.
• Document model logic, features, assumptions, limitations, and validation results in a way that business and technical stakeholders can understand.

Production ML and MLOps

• Partner with data engineering, platform engineering, and application engineering teams to move models from experimentation into reliable…